RAG over Thinking Traces Can Improve Reasoning Tasks
cs.IR, cs.AI, cs.CL
Submitted: 2026-05-05
Updated: 2026-09-06
Code: https://github.com/Narabzad/t3
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
- MemR$^3$: Memory Retrieval via Reflective Reasoning for LLM Agents
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Gemini: A Family of Highly Capable Multimodal Models
- Great Memory, Shallow Reasoning: Limits of $k$NN-LMs
- OpenThoughts: Data Recipes for Reasoning Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Teaching Small Language Models to Reason
- Large Language Models Are Reasoning Teachers
- s1: Simple test-time scaling
- Unsupervised Dense Information Retrieval with Contrastive Learning
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference
- How Much Can RAG Help the Reasoning of LLM?
- Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks
- gpt-oss-120b & gpt-oss-20b Model Card
- OpenAI GPT-5 System Card
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Code Llama: Open Foundation Models for Code
- Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
- UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG